© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77952
    Prev
    Next
    INDEX
    Explanations

    Philadelphia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ódromo
    -0.91
    rijf
    -0.85
     Côte
    -0.79
    ToTensor
    -0.78
    ători
    -0.78
     משת
    -0.77
    NBT
    -0.75
    其它
    -0.75
    celana
    -0.74
     modifi
    -0.74
    POSITIVE LOGITS
     ancla
    0.73
     direito
    0.71
     Philly
    0.70
     niew
    0.69
    philly
    0.69
     pł
    0.68
     Jugend
    0.68
    inquirer
    0.67
    贞
    0.67
     end
    0.66
    Activations Density 0.063%

    No Known Activations